M³vit: Mixture-of-experts vision transformer for efficient multi-task learning with model-accelerator co-design
Multi-task learning (MTL) encapsulates multiple learned tasks in a single model and often
lets those tasks learn better jointly. Multi-tasking models have become successful and often …
lets those tasks learn better jointly. Multi-tasking models have become successful and often …
Adamv-moe: Adaptive multi-task vision mixture-of-experts
Abstract Sparsely activated Mixture-of-Experts (MoE) is becoming a promising paradigm for
multi-task learning (MTL). Instead of compressing multiple tasks' knowledge into a single …
multi-task learning (MTL). Instead of compressing multiple tasks' knowledge into a single …
Sparse moe as the new dropout: Scaling dense and self-slimmable transformers
Despite their remarkable achievement, gigantic transformers encounter significant
drawbacks, including exorbitant computational and memory footprints during training, as …
drawbacks, including exorbitant computational and memory footprints during training, as …
Bridging remote sensors with multisensor geospatial foundation models
In the realm of geospatial analysis the diversity of remote sensors encompassing both
optical and microwave technologies offers a wealth of distinct observational capabilities …
optical and microwave technologies offers a wealth of distinct observational capabilities …
Multimodal clinical trial outcome prediction with large language models
The clinical trial is a pivotal and costly process, often spanning multiple years and requiring
substantial financial resources. Therefore, the development of clinical trial outcome …
substantial financial resources. Therefore, the development of clinical trial outcome …
DynaShare: task and instance conditioned parameter sharing for multi-task learning
Multi-task networks rely on effective parameter sharing to achieve robust generalization
across tasks. In this paper, we present a novel parameter sharing method for multi-task …
across tasks. In this paper, we present a novel parameter sharing method for multi-task …
Mncm: multi-level network cascades model for multi-task learning
H Wu - Proceedings of the 31st ACM International Conference …, 2022 - dl.acm.org
Recently, multi-task learning based on the deep neural network has been successfully
applied in many recommender system scenarios. The prediction quality of current …
applied in many recommender system scenarios. The prediction quality of current …
Sparse moe as a new treatment: Addressing forgetting, fitting, learning issues in multi-modal multi-task learning
Sparse Mixture-of-Experts (SMoE) is a promising paradigm that can be easily tailored for
multi-task learning. Its conditional computing nature allows us to organically allocate …
multi-task learning. Its conditional computing nature allows us to organically allocate …
Exploiting graph structured cross-domain representation for multi-domain recommendation
A Ariza-Casabona, B Twardowski… - European Conference on …, 2023 - Springer
Multi-domain recommender systems benefit from cross-domain representation learning and
positive knowledge transfer. Both can be achieved by introducing a specific modeling of …
positive knowledge transfer. Both can be achieved by introducing a specific modeling of …
Multitask learning of a biophysically-detailed neuron model
J Verhellen, K Beshkov, S Amundsen… - PLOS Computational …, 2024 - journals.plos.org
The human brain operates at multiple levels, from molecules to circuits, and understanding
these complex processes requires integrated research efforts. Simulating biophysically …
these complex processes requires integrated research efforts. Simulating biophysically …